import pandas as pd
import numpy as np
from pandas_profiling import ProfileReport
import seaborn as sns
import altair as alt

%run src/data_download.py --url=https://archive.ics.uci.edu/ml/machine-learning-databases/wine-quality/winequality-red.csv --delim=";" --filepath=data/ --filename=redwine

data_red = pd.read_csv("data/redwine", ",")

data_red = data_red.rename(columns=lambda x: x.replace(" ","_"))
data_red['quality_level'] = ["Excellent" if x >= 7 else "Good" if x >= 5 else "Bad" for x in data_red['quality']]
data_red['wine_type']= "red"
data_red.head()

	fixed_acidity	volatile_acidity	citric_acid	residual_sugar	chlorides	free_sulfur_dioxide	total_sulfur_dioxide	density	pH	sulphates	alcohol	quality	quality_level	wine_type
0	7.4	0.70	0.00	1.9	0.076	11.0	34.0	0.9978	3.51	0.56	9.4	5	Good	red
1	7.8	0.88	0.00	2.6	0.098	25.0	67.0	0.9968	3.20	0.68	9.8	5	Good	red
2	7.8	0.76	0.04	2.3	0.092	15.0	54.0	0.9970	3.26	0.65	9.8	5	Good	red
3	11.2	0.28	0.56	1.9	0.075	17.0	60.0	0.9980	3.16	0.58	9.8	6	Good	red
4	7.4	0.70	0.00	1.9	0.076	11.0	34.0	0.9978	3.51	0.56	9.4	5	Good	red

data_red.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 1599 entries, 0 to 1598
Data columns (total 14 columns):
 #   Column                Non-Null Count  Dtype  
---  ------                --------------  -----  
 0   fixed_acidity         1599 non-null   float64
 1   volatile_acidity      1599 non-null   float64
 2   citric_acid           1599 non-null   float64
 3   residual_sugar        1599 non-null   float64
 4   chlorides             1599 non-null   float64
 5   free_sulfur_dioxide   1599 non-null   float64
 6   total_sulfur_dioxide  1599 non-null   float64
 7   density               1599 non-null   float64
 8   pH                    1599 non-null   float64
 9   sulphates             1599 non-null   float64
 10  alcohol               1599 non-null   float64
 11  quality               1599 non-null   int64  
 12  quality_level         1599 non-null   object 
 13  wine_type             1599 non-null   object 
dtypes: float64(11), int64(1), object(2)
memory usage: 175.0+ KB

Class imbalance

alt.Chart(data_red).mark_bar().encode(
    alt.X('quality_level'),
    alt.Y('count()')
).properties(width = 200)

%run src/data_download.py --url=https://archive.ics.uci.edu/ml/machine-learning-databases/wine-quality/winequality-white.csv --delim=";" --filepath=data/ --filename=whitewine

data_white= pd.read_csv("data/whitewine", ",")

data_white = data_white.rename(columns=lambda x: x.replace(" ","_"))
data_white['quality_level'] = ["Excellent" if x >= 7 else "Good" if x >= 5 else "Bad" for x in data_white['quality']]
data_white['wine_type']= "white"
data_white.head()

	fixed_acidity	volatile_acidity	citric_acid	residual_sugar	chlorides	free_sulfur_dioxide	total_sulfur_dioxide	density	pH	sulphates	alcohol	quality	quality_level	wine_type
0	7.0	0.27	0.36	20.7	0.045	45.0	170.0	1.0010	3.00	0.45	8.8	6	Good	white
1	6.3	0.30	0.34	1.6	0.049	14.0	132.0	0.9940	3.30	0.49	9.5	6	Good	white
2	8.1	0.28	0.40	6.9	0.050	30.0	97.0	0.9951	3.26	0.44	10.1	6	Good	white
3	7.2	0.23	0.32	8.5	0.058	47.0	186.0	0.9956	3.19	0.40	9.9	6	Good	white
4	7.2	0.23	0.32	8.5	0.058	47.0	186.0	0.9956	3.19	0.40	9.9	6	Good	white

alt.Chart(data_white).mark_bar().encode(
    alt.X('quality_level'),
    alt.Y('count()')
).properties(width = 200)

data_red.shape

(1599, 14)

data_white.shape

(4898, 14)

full_data = pd.concat([data_white, data_red], axis=0)

full_data.shape

(6497, 14)

full_data.head(4)

	fixed_acidity	volatile_acidity	citric_acid	residual_sugar	chlorides	free_sulfur_dioxide	total_sulfur_dioxide	density	pH	sulphates	alcohol	quality	quality_level	wine_type
0	7.0	0.27	0.36	20.7	0.045	45.0	170.0	1.0010	3.00	0.45	8.8	6	Good	white
1	6.3	0.30	0.34	1.6	0.049	14.0	132.0	0.9940	3.30	0.49	9.5	6	Good	white
2	8.1	0.28	0.40	6.9	0.050	30.0	97.0	0.9951	3.26	0.44	10.1	6	Good	white
3	7.2	0.23	0.32	8.5	0.058	47.0	186.0	0.9956	3.19	0.40	9.9	6	Good	white

profile = ProfileReport(full_data)

profile

profile.to_file(output_file="data/output.html")

# Missing Values
print(full_data.isna().sum())

fixed_acidity           0
volatile_acidity        0
citric_acid             0
residual_sugar          0
chlorides               0
free_sulfur_dioxide     0
total_sulfur_dioxide    0
density                 0
pH                      0
sulphates               0
alcohol                 0
quality                 0
quality_level           0
wine_type               0
dtype: int64

No missing values

alt.data_transformers.disable_max_rows()
alt.Chart(full_data).mark_bar().encode(
    alt.X('quality_level', title = 'Quality Level'),
    alt.Y('count()', title = 'Number of counts'),
    alt.Color('wine_type', legend=None),
    alt.Column('wine_type', title = "Wine Type")).properties(width = 200)

#full_data.hist(figsize=(10,10))

data_num = full_data.loc[:,'fixed_acidity':'alcohol']
num_list = list(data_num.columns)

alt.Chart(full_data).mark_bar().encode(
    alt.X (alt.repeat('repeat'), bin = alt.Bin(maxbins = 20), type = 'quantitative'),
    alt.Y ('count()',title = "Count"),
    alt.Color ('wine_type'),
).properties(
    height = 100,
).properties(width = 200).repeat(repeat = num_list, columns = 3)